© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 1092
    Prev
    Next
    INDEX
    Explanations

    years written in the style of academic citations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -0.68
     الحره
    -0.62
    Tikang
    -0.58
    Geplaatst
    -0.57
    اریخ
    -0.56
    NavController
    -0.54
    Gemeinden
    -0.53
    ApiProperty
    -0.52
     officially
    -0.52
    chwitz
    -0.52
    POSITIVE LOGITS
     yılı
    0.63
     resourceCulture
    0.59
    TintMode
    0.58
    년
    0.55
    adaptiveStyles
    0.54
    numerusform
    0.52
    SPATH
    0.50
     lenker
    0.50
    tvguidetime
    0.50
    年
    0.48
    Activations Density 0.259%

    No Known Activations